{"id":"https://openalex.org/W4412588058","doi":"https://doi.org/10.1145/3721238.3730670","title":"IP-Prompter: Training-Free Theme-Specific Image Generation via Dynamic Visual Prompting","display_name":"IP-Prompter: Training-Free Theme-Specific Image Generation via Dynamic Visual Prompting","publication_year":2025,"publication_date":"2025-07-23","ids":{"openalex":"https://openalex.org/W4412588058","doi":"https://doi.org/10.1145/3721238.3730670"},"language":"en","primary_location":{"id":"doi:10.1145/3721238.3730670","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721238.3730670","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3721238.3730670","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100398013","display_name":"Yuxin Zhang","orcid":"https://orcid.org/0000-0001-6433-2678"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuxin Zhang","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6433-2678","affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111176578","display_name":"Minyan Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minyan Luo","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-2675-1650","affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069298091","display_name":"Weiming Dong","orcid":"https://orcid.org/0000-0001-6502-145X"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiming Dong","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6502-145X","affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050400885","display_name":"Xiao Yang","orcid":"https://orcid.org/0000-0002-6010-9281"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Yang","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-2411-3594","affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101795031","display_name":"Haibin Huang","orcid":"https://orcid.org/0000-0002-7787-6428"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haibin Huang","raw_affiliation_strings":["ByteDance Inc., San Jose, USA"],"raw_orcid":"https://orcid.org/0000-0002-7787-6428","affiliations":[{"raw_affiliation_string":"ByteDance Inc., San Jose, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025046851","display_name":"Chongyang Ma","orcid":"https://orcid.org/0000-0002-8243-9513"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chongyang Ma","raw_affiliation_strings":["ByteDance Inc., San Jose, USA"],"raw_orcid":"https://orcid.org/0000-0002-8243-9513","affiliations":[{"raw_affiliation_string":"ByteDance Inc., San Jose, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036489223","display_name":"Oliver Deu\u00dfen","orcid":"https://orcid.org/0000-0001-5803-2185"},"institutions":[{"id":"https://openalex.org/I189712700","display_name":"University of Konstanz","ror":"https://ror.org/0546hnb39","country_code":"DE","type":"education","lineage":["https://openalex.org/I189712700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Oliver Deussen","raw_affiliation_strings":["University of Konstanz, Konstanz, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5803-2185","affiliations":[{"raw_affiliation_string":"University of Konstanz, Konstanz, Germany","institution_ids":["https://openalex.org/I189712700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050657606","display_name":"Tong\u2010Yee Lee","orcid":"https://orcid.org/0000-0001-6699-2944"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tong-Yee Lee","raw_affiliation_strings":["National Cheng-Kung University, Tainan, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-6699-2944","affiliations":[{"raw_affiliation_string":"National Cheng-Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022636178","display_name":"Changsheng Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Xu","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8343-9665","affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100398013"],"corresponding_institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":1.1332,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80194185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9850999712944031,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6692208647727966},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5337157249450684},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5306115746498108},{"id":"https://openalex.org/keywords/theme","display_name":"Theme (computing)","score":0.5013675689697266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4605270028114319},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.36658090353012085},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10319772362709045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6692208647727966},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5337157249450684},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5306115746498108},{"id":"https://openalex.org/C33566652","wikidata":"https://www.wikidata.org/wiki/Q1065927","display_name":"Theme (computing)","level":2,"score":0.5013675689697266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4605270028114319},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.36658090353012085},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10319772362709045},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3721238.3730670","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721238.3730670","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:kops.uni-konstanz.de:123456789/76633","is_oa":true,"landing_page_url":"http://nbn-resolving.de/urn:nbn:de:bsz:352-2-1fi6f1az88zey2","pdf_url":null,"source":{"id":"https://openalex.org/S4377196311","display_name":"KOPS (University of Konstanz)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I189712700","host_organization_name":"University of Konstanz","host_organization_lineage":["https://openalex.org/I189712700"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3721238.3730670","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721238.3730670","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6258788437","display_name":null,"funder_award_id":"111-2221-E-006-112-MY3","funder_id":"https://openalex.org/F2461203286","funder_display_name":"National Science and Technology Council"}],"funders":[{"id":"https://openalex.org/F2461203286","display_name":"National Science and Technology Council","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W3023742835","https://openalex.org/W4310895557","https://openalex.org/W4312697499","https://openalex.org/W4386071613","https://openalex.org/W4386072096","https://openalex.org/W4386076425","https://openalex.org/W4389334940","https://openalex.org/W4389334989","https://openalex.org/W4389539271","https://openalex.org/W4389574988","https://openalex.org/W4390872325","https://openalex.org/W4390872421","https://openalex.org/W4390873054","https://openalex.org/W4390874393","https://openalex.org/W4393148714","https://openalex.org/W4394844375","https://openalex.org/W4400582187","https://openalex.org/W4400818431","https://openalex.org/W4400822031","https://openalex.org/W4402667886","https://openalex.org/W4402703034","https://openalex.org/W4402703076","https://openalex.org/W4402703083","https://openalex.org/W4402716004","https://openalex.org/W4402726936","https://openalex.org/W4402774219","https://openalex.org/W4402774246","https://openalex.org/W4402951578","https://openalex.org/W4403791325","https://openalex.org/W4404984122","https://openalex.org/W4410773830","https://openalex.org/W6601375265","https://openalex.org/W6863511876"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"The":[0],"stories":[1],"and":[2,62,77,93,182,201,218,227,233],"characters":[3],"that":[4,141,212],"captivate":[5],"us":[6],"as":[7,18,59,110,121],"we":[8,126,165],"grow":[9],"up":[10],"shape":[11],"unique":[12],"fantasy":[13],"worlds,":[14],"with":[15,32,87],"images":[16,80,109,144],"serving":[17],"the":[19,153,180],"primary":[20],"medium":[21],"for":[22,236],"visually":[23],"experiencing":[24],"these":[25],"realms.":[26],"Personalizing":[27],"generative":[28,146],"models":[29,106,118],"through":[30],"fine-tuning":[31,83],"theme-specific":[33,53,79,237],"data":[34],"has":[35],"become":[36],"a":[37,68,100,129,139,167,231],"prevalent":[38],"approach":[39,188],"in":[40,220],"text-to-image":[41],"generation.":[42,204,239],"However,":[43],"unlike":[44],"object":[45],"customization,":[46],"which":[47,173],"focuses":[48],"on":[49],"learning":[50],"specific":[51],"objects,":[52],"generation":[54,105,133],"encompasses":[55],"diverse":[56,190],"elements":[57],"such":[58],"characters,":[60],"scenes,":[61],"objects.":[63],"Such":[64],"diversity":[65],"also":[66],"introduces":[67,136],"key":[69],"challenge:":[70],"how":[71,115],"to":[72,114,150,178],"adaptively":[73],"generate":[74],"multi-character,":[75],"multi-concept,":[76],"continuous":[78],"(TSI).":[81],"Moreover,":[82],"approaches":[84],"often":[85],"come":[86],"significant":[88],"computational":[89],"overhead,":[90],"time":[91],"costs,":[92],"risks":[94],"of":[95,184],"overfitting.":[96],"This":[97],"paper":[98],"explores":[99],"fundamental":[101],"question:":[102],"Can":[103],"image":[104,203,238],"directly":[107],"leverage":[108],"contextual":[111],"input,":[112],"similarly":[113],"large":[116],"language":[117],"use":[119],"text":[120,228],"context?":[122],"To":[123,160],"address":[124],"this,":[125],"present":[127],"IP-Prompter,":[128],"novel":[130],"training-free":[131],"TSI":[132],"method.":[134],"IP-Prompter":[135,213],"visual":[137,176],"prompting,":[138],"mechanism":[140],"integrates":[142],"reference":[143],"into":[145],"models,":[147],"allowing":[148],"users":[149],"seamlessly":[151],"specify":[152],"target":[154],"theme":[155],"without":[156],"requiring":[157],"additional":[158],"training.":[159],"further":[161],"enhance":[162],"this":[163],"process,":[164],"propose":[166],"Dynamic":[168],"Visual":[169],"Prompting":[170],"(DVP)":[171],"mechanism,":[172],"iteratively":[174],"optimizes":[175],"prompts":[177],"improve":[179],"accuracy":[181],"quality":[183],"generated":[185],"images.":[186],"Our":[187,240],"enables":[189],"applications,":[191],"including":[192],"consistent":[193],"story":[194],"generation,":[195,200],"character":[196,199,222],"design,":[197],"realistic":[198],"style-guided":[202],"Comparative":[205],"evaluations":[206],"against":[207],"state-of-the-art":[208],"personalization":[209],"methods":[210],"demonstrate":[211],"achieves":[214],"significantly":[215],"better":[216],"results":[217],"excels":[219],"maintaining":[221],"identity":[223],"preserving,":[224],"style":[225],"consistency":[226],"alignment,":[229],"offering":[230],"robust":[232],"flexible":[234],"solution":[235],"project":[241],"page:":[242],"https://ip-prompter.github.io/.":[243]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
